Video Transcription & Indexing Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

namespace = client.namespaces.create(name="transcripts")
collection = client.collections.create(
    namespace_id=namespace.id,
    name="meetings",
    extractors=["audio-transcription", "speaker-diarization"]
)

# Upload videos - transcription happens automatically
client.buckets.upload(
    collection_id=collection.id,
    url="s3://your-bucket/meeting-recordings/"
)

# Retrieve transcript
docs = client.documents.search(
    namespace_id=namespace.id,
    collection_ids=[collection.id],
    query="action items from last week"
)